具有中性项的全局吸引神经网络集

IF 2.6 3区数学 Q1 MATHEMATICS, APPLIED Nonlinear Analysis-Modelling and Control Pub Date : 2023-01-02 DOI:10.15388/namc.2023.28.30517

Xili Wu, Liangwei Wang, Zhengwen Tu, Yuming Feng

{"title":"具有中性项的全局吸引神经网络集","authors":"Xili Wu, Liangwei Wang, Zhengwen Tu, Yuming Feng","doi":"10.15388/namc.2023.28.30517","DOIUrl":null,"url":null,"abstract":"This paper investigates the global attractive set of neural networks with neutral item. To better deal with the neutral terms, different types of activation functions are considered. Based on matrix measures, inequality techniques, and Lyapunov theory, three new types of Lyapunov functions are designed to find the global attractive set of the system. We give out a simulation example to verify the validity of theory results. The result is very inclusive, whether the system has equilibrium or not. As long as the system is stable, we can find its global attractive set.","PeriodicalId":49286,"journal":{"name":"Nonlinear Analysis-Modelling and Control","volume":" ","pages":""},"PeriodicalIF":2.6000,"publicationDate":"2023-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Global attractive set of neural networks with neutral item\",\"authors\":\"Xili Wu, Liangwei Wang, Zhengwen Tu, Yuming Feng\",\"doi\":\"10.15388/namc.2023.28.30517\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This paper investigates the global attractive set of neural networks with neutral item. To better deal with the neutral terms, different types of activation functions are considered. Based on matrix measures, inequality techniques, and Lyapunov theory, three new types of Lyapunov functions are designed to find the global attractive set of the system. We give out a simulation example to verify the validity of theory results. The result is very inclusive, whether the system has equilibrium or not. As long as the system is stable, we can find its global attractive set.\",\"PeriodicalId\":49286,\"journal\":{\"name\":\"Nonlinear Analysis-Modelling and Control\",\"volume\":\" \",\"pages\":\"\"},\"PeriodicalIF\":2.6000,\"publicationDate\":\"2023-01-02\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Nonlinear Analysis-Modelling and Control\",\"FirstCategoryId\":\"100\",\"ListUrlMain\":\"https://doi.org/10.15388/namc.2023.28.30517\",\"RegionNum\":3,\"RegionCategory\":\"数学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"MATHEMATICS, APPLIED\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Nonlinear Analysis-Modelling and Control","FirstCategoryId":"100","ListUrlMain":"https://doi.org/10.15388/namc.2023.28.30517","RegionNum":3,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"MATHEMATICS, APPLIED","Score":null,"Total":0}

引用次数: 0

摘要

研究了具有中性项的神经网络的全局吸引集。为了更好地处理中性项，考虑了不同类型的激活函数。基于矩阵测度、不等式技术和Lyapunov理论，设计了三种新的Lyapunov函数来寻找系统的全局吸引集。最后通过仿真实例验证了理论结果的有效性。无论系统是否均衡，其结果都是非常包容的。只要系统是稳定的，我们就可以找到它的全局吸引集。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

Global attractive set of neural networks with neutral item

This paper investigates the global attractive set of neural networks with neutral item. To better deal with the neutral terms, different types of activation functions are considered. Based on matrix measures, inequality techniques, and Lyapunov theory, three new types of Lyapunov functions are designed to find the global attractive set of the system. We give out a simulation example to verify the validity of theory results. The result is very inclusive, whether the system has equilibrium or not. As long as the system is stable, we can find its global attractive set.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Nonlinear Analysis-Modelling and Control MATHEMATICS, APPLIED-MATHEMATICS, INTERDISCIPLINARY APPLICATIONS

CiteScore

3.80

自引率

10.00%

发文量

审稿时长

9.6 months

期刊介绍： The scope of the journal is to provide a multidisciplinary forum for scientists, researchers and engineers involved in research and design of nonlinear processes and phenomena, including the nonlinear modelling of phenomena of the nature. The journal accepts contributions on nonlinear phenomena and processes in any field of science and technology. The aims of the journal are: to provide a presentation of theoretical results and applications; to cover research results of multidisciplinary interest; to provide fast publishing of quality papers by extensive work of editors and referees; to provide an early access to the information by presenting the complete papers on Internet.